High-dimensional and high-complexity unsupervised abnormal data recognition with neural networks remains an open research question. We propose a multi-level Variational Auto Encoder (VAE) structure in this work. First, based on traditional VAE, we deconstruct the original data using convolution kernels of different specifications to establish multiple feature latent spaces, thereby reducing the excessive data aggregation in the latent space. Then we use an equal-window convolution kernel to fuse feature blocks of different sizes, thereby transforming local features into globally identifiable features. Moreover, the model structure shortens the distance between the sub-feature block and the output end-point, reducing the training inefficiency caused by the vanishing gradient.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Multi-level Variational Auto Encoder for Unsupervised Abnormal Data Recognition


    Contributors:
    Guan, Yaonan (author) / Yu, Yaru (author) / Wang, Gang (author) / Li, Dewei (author)


    Publication date :

    2022-06-27


    Size :

    1246690 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Variational auto encoder for mixed data types

    European Patent Office | 2020

    Free access

    AVAE: Adversarial Variational Auto Encoder

    Plumerault, Antoine / Borgne, Hervé Le / Hudelot, Céline | ArXiv | 2020

    Free access

    Disentangled Variational Auto-Encoder for Semi-supervised Learning

    Li, Yang / Pan, Quan / Wang, Suhang et al. | ArXiv | 2017

    Free access


    Disentangling Latent Factors of Variational Auto-Encoder with Whitening

    Hahn, Sangchul / Choi, Heeyoul | ArXiv | 2018

    Free access